© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 13097
    Prev
    Next
    INDEX
    Explanations

    unsavory allegations, questionable conduct, dirty dairying

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    unos
    -0.20
    ç´§å¼ł
    -0.20
    çģ½
    -0.19
     cháy
    -0.18
    ONSE
    -0.18
    çĹĩ
    -0.18
    çĪĨåıij
    -0.18
    çģ¾
    -0.18
     EÄŁitim
    -0.18
    çģ¾éļ¾
    -0.18
    POSITIVE LOGITS
     tactics
    0.23
     practices
    0.23
     deeds
    0.23
    æīĭ段
    0.23
     Tactics
    0.22
    /il
    0.22
     dealings
    0.21
    ulous
    0.21
    è¡Į为
    0.21
    èµĸ
    0.20
    Activations Density 0.031%

    No Known Activations